INDEX

Explanations

references and citations related to resources and data structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Tokens followed by a number

np_acts-logits-general · gemini-2.0-flash

resource group identifiers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.56

BagLayout

-0.53

'{@

-0.52

Tikang

-0.50

 Titanium

-0.49

 webdriver

-0.46

Yum

-0.46

Yo

-0.44

SequentialGroup

-0.44

ZF

-0.44

POSITIVE LOGITS

InjectAttribute

0.67

 समीक्षाओं

0.66

├──

0.55

 Allociné

0.55

évaluateur

0.50

amaged

0.50

gnore

0.47

 disambiguazione

0.46

Personendaten

0.45

 отлича

0.45

Activations Density 0.230%

references and citations related to resources and data structures

Tokens followed by a number

resource group identifiers

No Comments

No Known Activations